Automatic Image Interpolation Using Homography
- PDF / 3,419,944 Bytes
- 10 Pages / 504.63 x 612.36 pts Page_size
- 91 Downloads / 256 Views
PublisherName
:
Springer International Publishing
PublisherLocation
:
Cham
PublisherImprintName
:
Springer
Automatic Image Interpolation Using Homography ArticleInfo
ArticleID
:
2738
ArticleDOI
:
10.1155/2010/307546
ArticleCitationID
:
307546
ArticleSequenceNumber
:
80
ArticleCategory
:
Research Article
ArticleFirstPage
:
1
ArticleLastPage
: RegistrationDate : 2009–7–8
ArticleHistory
:
ArticleCopyright
:
ArticleGrants
:
ArticleContext
:
Received
: 2009–7–8
Revised
: 2010–1–25
Accepted
: 2010–4–13
OnlineDate
: 2010–5–20
The Author(s)2010 This article is published under license to BioMed Central Ltd. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
136342010201011
Yi-Leh Wu,Aff1
Email: [email protected]
Cheng-Yuan Tang,Aff2
Corresponding Affiliation: Aff2 Email: [email protected]
Maw-Kae Hor,Aff3
Email: [email protected]
Chi-Tsung Liu,Aff2
Email: [email protected]
Aff1 Aff2 Aff3
Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, no. 43, Section 4, Keelung Rood, Taipei 106, Taiwan, 2Department of Information ManagementHuafan University, no. 1, Huafan Rood Shihding TownshipTaipei 2,2301Taiwanhfu.edu.tw, Department of Computer Science, National Cheng Chi University, no. 64, Section 2, ZhiNan Rood, Wenshan District, Taipei 11605, Taiwan,
While taking photographs, we often face the problem that unwanted foreground objects (e.g., vehicles, signs, and pedestrians) occlude the main subject(s). We propose to apply image interpolation (also known ) techniques to remove unwanted objects in the photographs and as inpainting to automatically patch the vacancy after the unwanted objects are removed. When given only a single image, if the information loss after the unwanted objects in images being removed is too great, the patching results are usually unsatisfactory. The proposed inpainting techniques employ the homographic constraints in geometry to incorporate multiple images taken from different viewpoints. Our experiment results showed that the proposed techniques could effectively reduce process in searching for potential patches from multiple input images and decide the best patches for the missing regions.
1. Introduction Historical sites represent the culture of a country. As a result, preserving historical sites becomes a more and more important trend in recent years. Today, the technological advancement of digital techniques can help building 3D models of the historical sites under preservation and presenting them by virtual reality. It can keep the original features of the historic sites for a long period of time. Figure 1 shows the computerized models of
the Beipu Township, a national historical site in the Hsinchu County, Taiwan, with 3D models overlaid on satellite images. With the computerized models, visitors can walk
Data Loading...
